© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57169
    Prev
    Next
    INDEX
    Explanations

    convenience and accessibility

    np_acts-logits-general · gemini-2.5-flash-lite

    inaccessible or unavailable things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ウォッチ
    0.39
     credible
    0.38
     adverts
    0.38
    னுடைய
    0.38
     ბ
    0.37
     advertis
    0.37
     Briggs
    0.37
    헷
    0.37
    辨
    0.36
     energized
    0.36
    POSITIVE LOGITS
     inaccessible
    1.02
     unavailable
    0.84
     unreachable
    0.83
    unavailable
    0.77
     Unavailable
    0.70
    Absent
    0.64
     unattainable
    0.64
     שלא
    0.62
    Unavailable
    0.61
     unavailability
    0.61
    Activations Density 0.145%

    No Known Activations